{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0034315127251930227,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003812791916881136,
      "grad_norm": 2.743847131729126,
      "learning_rate": 2e-05,
      "loss": 12.583,
      "step": 1
    },
    {
      "epoch": 0.0003812791916881136,
      "eval_loss": 2.7877824306488037,
      "eval_runtime": 91.7699,
      "eval_samples_per_second": 12.041,
      "eval_steps_per_second": 6.026,
      "step": 1
    },
    {
      "epoch": 0.0007625583833762272,
      "grad_norm": 1.5053740739822388,
      "learning_rate": 4e-05,
      "loss": 9.648,
      "step": 2
    },
    {
      "epoch": 0.001143837575064341,
      "grad_norm": 2.1065523624420166,
      "learning_rate": 6e-05,
      "loss": 11.0947,
      "step": 3
    },
    {
      "epoch": 0.001143837575064341,
      "eval_loss": 2.7865514755249023,
      "eval_runtime": 94.7829,
      "eval_samples_per_second": 11.658,
      "eval_steps_per_second": 5.834,
      "step": 3
    },
    {
      "epoch": 0.0015251167667524545,
      "grad_norm": 2.0303115844726562,
      "learning_rate": 8e-05,
      "loss": 11.5601,
      "step": 4
    },
    {
      "epoch": 0.0019063959584405682,
      "grad_norm": 1.3866581916809082,
      "learning_rate": 0.0001,
      "loss": 10.9195,
      "step": 5
    },
    {
      "epoch": 0.002287675150128682,
      "grad_norm": 1.8674153089523315,
      "learning_rate": 0.00012,
      "loss": 11.3511,
      "step": 6
    },
    {
      "epoch": 0.002287675150128682,
      "eval_loss": 2.7706356048583984,
      "eval_runtime": 95.9066,
      "eval_samples_per_second": 11.522,
      "eval_steps_per_second": 5.766,
      "step": 6
    },
    {
      "epoch": 0.002668954341816795,
      "grad_norm": 1.9716304540634155,
      "learning_rate": 0.00014,
      "loss": 10.1866,
      "step": 7
    },
    {
      "epoch": 0.003050233533504909,
      "grad_norm": 2.446058511734009,
      "learning_rate": 0.00016,
      "loss": 11.8968,
      "step": 8
    },
    {
      "epoch": 0.0034315127251930227,
      "grad_norm": 2.609543800354004,
      "learning_rate": 0.00018,
      "loss": 10.3168,
      "step": 9
    },
    {
      "epoch": 0.0034315127251930227,
      "eval_loss": 2.709000825881958,
      "eval_runtime": 95.8656,
      "eval_samples_per_second": 11.527,
      "eval_steps_per_second": 5.768,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1465874317836288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}